IEEE Transactions on Automatic Control

最新文章

• Optimal Control of a Large Population of Randomly Interrogated Interacting Agents AI翻译
  作者：Komaee, Arash
  作者单位：Southern Illinois University System; Southern Illinois University
  摘要：This article investigates a stochastic optimal control problem with linear Gaussian dynamics, quadratic performance measure, but non-Gaussian observations. The linear Gaussian dynamics characterizes a large number of interacting agents evolving under a centralized control and external disturbances. The aggregate state of the agents is only partially known to the centralized controller by means of the samples taken randomly in time and from anonymous randomly selected agents. Due to the removal...
• Discrete-Time Switching Systems as Difference Inclusions: Deducing Converse Lyapunov Results for the Former From Those for the Latter AI翻译
  作者：Goebel, Rafal
  作者单位：Loyola University Chicago
  摘要：Nonlinear discrete-time switching systems under mode-dependent switching and dwell-time constraints are modeled by difference inclusions. Novel proofs of converse Lyapunov results are obtained for the switching systems as consequences of a converse Lyapunov result for a difference inclusion.
• Sample Complexity and Overparameterization Bounds for Temporal-Difference Learning With Neural Network Approximation AI翻译
  作者：Cayci, Semih; Satpathi, Siddhartha; He, Niao; Srikant, R.
  作者单位：University of Illinois System; University of Illinois Urbana-Champaign; RWTH Aachen University; University of Illinois System; University of Illinois Urbana-Champaign; Mayo Clinic; Swiss Federal Institutes of Technology Domain; ETH Zurich; University of Illinois System; University of Illinois Urbana-Champaign
  摘要：In this article, we study the dynamics of temporal-difference (TD) learning with neural network-based value function approximation over a general state space, namely, neural TD learning. We consider two practically used algorithms, projection-free and max-norm regularized neural TD learning, and establish the first convergence bounds for these algorithms. An interesting observation from our results is that max-norm regularization can dramatically improve the performance of TD learning algorith...
• A General Framework for Learning-Based Distributionally Robust MPC of Markov Jump Systems AI翻译
  作者：Schuurmans, Mathijs; Patrinos, Panagiotis
  作者单位：KU Leuven
  摘要：In this article, we present a data-driven learning model predictive control (MPC) scheme for chance-constrained Markov jump systems with unknown switching probabilities. Using samples of the underlying Markov chain, ambiguity sets of transition probabilities are estimated, which include the true conditional probability distributions with high probability. These sets are updated online and used to formulate a time-varying, risk-averse optimal control problem. We prove recursive feasibility of t...
• On-the-Fly Control of Unknown Nonlinear Systems With Sublinear Regret AI翻译
  作者：Vinod, Abraham P.; Israel, Arie; Topcu, Ufuk
  作者单位：University of Texas System; University of Texas Austin; University of Texas System; University of Texas Austin
  摘要：We study the problem of data-driven, constrained control of unknown nonlinear dynamics from a single ongoing and finite-horizon trajectory. We consider a one-step optimal control problem with a smooth, black-box objective, typically a composition of a known cost function and the unknown dynamics. We investigate an on-the-fly control paradigm, i.e., at each time step, the evolution of the dynamics and the first-order information of the cost are provided only for the executed control action. We ...
• Solving Nonlinear Algebraic Loops Arising in Input-Saturated Feedbacks AI翻译
  作者：Blanchini, Franco; Giordano, Giulia; Riz, Francesco; Zaccarian, Luca
  作者单位：University of Udine; University of Trento; University of Trento; University of Trento; Centre National de la Recherche Scientifique (CNRS); Universite de Toulouse
  摘要：In this article, we propose a dynamic augmentation scheme for the asymptotic solution of the nonlinear algebraic loops arising in well-known input saturated feedbacks typically designed by solving linear matrix inequalities. We prove that the existing approach based on dynamic augmentation, which replaces the static loop by a dynamic one through the introduction of a sufficiently small time constant, works under some restrictive sufficient well-posedness conditions, requiring the existence of ...
• A Lyapunov-Based ISS Small-Gain Theorem for Infinite Networks of Nonlinear Systems AI翻译
  作者：Kawan, Christoph; Mironchenko, Andrii; Zamani, Majid
  作者单位：University of Munich; University of Passau; University of Colorado System; University of Colorado Boulder
  摘要：In this article, we show that an infinite network of input-to-state stable (ISS) subsystems, admitting ISS Lyapunov functions, itself admits an ISS Lyapunov function, provided that the couplings between the subsystems are sufficiently weak. The strength of the couplings is described in terms of the properties of an infinite-dimensional nonlinear positive operator, built from the interconnection gains. If this operator induces a uniformly globally asymptotically stable (UGAS) system, a Lyapunov...
• Prescribed-Time Output-Feedback Control of Stochastic Nonlinear Systems AI翻译
  作者：Li, Wuquan; Krstic, Miroslav
  作者单位：Ludong University; University of California System; University of California San Diego
  摘要：We present prescribed-time output-feedback-stabilizing designs for stochastic nonlinear strict-feedback systems. We first propose a new nonscaling output-feedback control scheme to solve the prescribed-time mean-square stabilization problem for stochastic nonlinear systems without sensor uncertainty. In this case, compared with the existing results on stochastic nonlinear prescribed-time stabilization, an appealing feature in our design is that the order of the scaling function in the controll...
• Linear-Quadratic Non-Zero Sum Backward Stochastic Differential Game With Overlapping Information AI翻译
  作者：Wu, Shuang
  作者单位：China University of Petroleum
  摘要：This article studies a linear quadratic non-zero sum stochastic differential game with overlapping information, where the state dynamics are described by a backward stochastic differential equation and the information obtained by two players has a common part but no inclusion relation. The open-loop Nash equilibrium strategy is given by some conditional mean-field stochastic differential equations. In addition, coupled Riccati equations are introduced to express the state feedback form of the ...
• Stabilization of Switched Linear Neutral Systems With Time-Scheduled Feedback Control Strategy AI翻译
  作者：Fei, Zhongyang; Chen, Weizhong; Zhao, Xudong; Ren, Shunqing
  作者单位：Dalian University of Technology; Dalian University of Technology; Harbin Institute of Technology
  摘要：This article is concerned with the stabilization of continuous-time switched linear neutral systems with tighter bounds on mode-dependent average dwell time. By introducing a novel time-scheduled control strategy, a switching-signal-based multiple discontinuous Lyapunov function (SMDLF) is constructed for continuous-time switched linear neutral systems, where the discontinuous points of the Lyapunov function during each mode-running interval are dynamically adjusted according to the actual sys...